Intelligent petroleum grading filtration control system with cascade feedback function

Abstract

The invention discloses an intelligent petroleum graded filtration control system with a cascade feedback function, and relates to the technical field of petroleum filtration, the system comprises a filtration mechanism acquisition module used for acquiring N stages of filtration mechanisms; the filtering continuity analysis module is used for performing filtering continuity analysis on two adjacent groups of filtering monitoring data sets; an abnormality filtering mechanism determination module; the feedback analysis module is used for carrying out feedback analysis on the abnormity filtering mechanism; the parallel feedback optimization module is used for performing parallel feedback optimization on the abnormity filtering mechanism; and the series feedback optimization module is used for carrying out series feedback optimization on the abnormity filtering mechanism. The technical problem that in the prior art, the overall filtering effect cannot be judged according to the possible efficiency difference of all stages of filtering mechanisms, and therefore the petroleum filtering efficiency and stability are affected is solved, and the purposes of real-time monitoring, accurate diagnosis and flexible feedback optimization are achieved through the multiple stages of filtering mechanisms. The petroleum filtering efficiency and the stability are improved.

Description

Technical Field

[0001] This invention relates to the field of petroleum filtration technology, and more specifically to an intelligent petroleum graded filtration control system with cascade feedback function. Background Technology

[0002] To remove impurities from petroleum and improve its quality, a multi-stage filtration system is typically used. This system removes impurities of varying sizes and properties from the petroleum through multiple filtration stages, ensuring its purity. However, multi-stage petroleum filtration systems require long-term stable operation and must maintain filtration effectiveness under various complex environments. Currently, the automation and intelligence levels of these systems are generally low, making it difficult to assess the overall filtration effect based on potential efficiency differences between each filtration stage, thus impacting filtration efficiency and stability. Summary of the Invention

[0003] This application provides an intelligent petroleum grading and filtration control system with cascade feedback function to solve the technical problem that the current petroleum grading and filtration devices have low levels of automation and intelligence, resulting in poor petroleum filtration efficiency and stability.

[0004] The first aspect of this application provides an intelligent petroleum graded filtration control system with cascaded feedback function. The system includes: a filtration mechanism acquisition module, used to acquire N-stage filtration mechanisms of a petroleum graded filtration device, where N is a positive integer greater than or equal to 2; a filtration continuity analysis module, used to monitor N sets of filtration monitoring datasets corresponding to the N-stage filtration mechanisms, perform filtration continuity analysis on adjacent sets of filtration monitoring datasets in the N sets of filtration monitoring datasets, and output N-1 filtration continuity indicators; and an abnormal filtration mechanism determination module, used to determine abnormal filtration mechanisms based on the N-1 filtration continuity indicators. The system includes: a feedback analysis module for identifying the configuration parameters of the anomaly filtering mechanism and inputting these parameters into an adaptive feedback module for analysis. The adaptive feedback module is a cascaded feedback module, comprising a parallel feedback module and a series feedback module. A parallel feedback optimization module is used to obtain a parallel fitness index based on the adaptive feedback module. If the parallel fitness index meets a preset threshold, parallel feedback optimization is performed on the anomaly filtering mechanism. A series feedback optimization module is used to perform series feedback optimization on the anomaly filtering mechanism if the parallel fitness index does not meet the preset threshold.

[0005] One or more technical solutions provided in this application have at least the following technical effects or advantages: This application provides an intelligent petroleum grading filtration control system with cascaded feedback function, relating to the field of petroleum filtration technology. By acquiring N sets of filtration monitoring datasets from N-stage filtration mechanisms of a petroleum grading filtration device, performing filtration continuity analysis, identifying abnormal filtration mechanisms, recognizing the mechanism configuration parameters of abnormal filtration mechanisms, and inputting them into an adaptive feedback module for feedback analysis, the system performs parallel or series feedback optimization on the abnormal filtration mechanisms based on the analysis results. This solves the technical problem in existing technologies where the overall filtration effect cannot be judged based on potential efficiency differences between filtration mechanisms at each stage, thus affecting petroleum filtration efficiency and stability. It achieves the technical effect of improving petroleum filtration efficiency and stability through real-time monitoring, accurate diagnosis, and flexible feedback optimization of multi-stage filtration mechanisms. Attached Figure Description

[0006] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0007] Figure 1 A schematic diagram of an intelligent petroleum graded filtration control system with cascaded feedback function is provided for an embodiment of this application; Figure 2 A schematic diagram of the process for performing filtration continuity analysis in an intelligent petroleum graded filtration control system with cascaded feedback function provided in an embodiment of this application; Figure 3 This is a schematic diagram illustrating the parallel feedback optimization of an abnormal filtration mechanism in an intelligent petroleum graded filtration control system with cascaded feedback function, provided as an embodiment of this application.

[0008] Explanation of reference numerals in the attached drawings: Filter mechanism acquisition module 11, Filter continuity analysis module 12, Abnormal filter mechanism determination module 13, Feedback analysis module 14, Parallel feedback optimization module 15, Series feedback optimization module 16. Detailed Implementation

[0009] This application provides an intelligent petroleum grading and filtration control system with cascade feedback function to solve the technical problem that the current petroleum grading and filtration devices have low levels of automation and intelligence, resulting in poor petroleum filtration efficiency and stability.

[0010] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0011] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or devices.

[0012] Example 1, as Figure 1 As shown, this application provides an intelligent petroleum graded filtration control system with cascaded feedback function, the system comprising: The filter mechanism acquisition module 11 is used to acquire the N-stage filter mechanism of the petroleum grading filter device, where N is a positive integer greater than or equal to 2.

[0013] Specifically, the main function of the filter mechanism acquisition module 11 in this application is to automatically identify and acquire information on each level of filter mechanism in the petroleum grading filtration device. In practical applications, multi-stage filtration is typically required for more effective petroleum filtration. Therefore, the petroleum grading filtration device is first scanned to determine the total number of filter mechanisms N, where N is a positive integer greater than or equal to 2. Further, detailed information on each filter mechanism is acquired, including the type of filter mechanism (e.g., particulate filter, activated carbon filter), the specifications of the filter mechanism (e.g., size, capacity), the current operating status of the filter mechanism (e.g., whether it is online, whether maintenance is required), and the performance parameters of the filter mechanism (e.g., filtration efficiency, pressure drop), serving as the basis for subsequent filtration continuity analysis, identification of abnormal filter mechanisms, and feedback optimization processes.

[0014] The filter continuity analysis module 12 is used to monitor N sets of filter monitoring datasets corresponding to the N-level filter mechanism, perform filter continuity analysis on the filter monitoring datasets of two adjacent sets in the N sets of filter monitoring datasets, and output N-1 filter continuity indicators.

[0015] Furthermore, such as Figure 2 As shown, the filter continuity analysis module 12 is also used to perform the following steps: P21: Each set of filtration monitoring datasets includes the oil medium flow rate, oil pressure difference, oil medium temperature, oil contaminant concentration before filtration, and oil contaminant concentration after filtration for the corresponding filtration mechanism; P22: Calculate the efficiency of the N-stage filtration mechanism based on the N sets of filtration monitoring datasets, and output N filtration efficiencies; P23: Generate N-1 filtration efficiency groups corresponding to two adjacent groups among the N filtration efficiencies; P24: Perform filtration efficiency continuity analysis on the N-1 filtration efficiency groups, and output N-1 filtration continuity indicators.

[0016] It should be understood that the main function of the filtration continuity analysis module 12 in this application is to monitor and analyze N sets of filtration monitoring datasets corresponding to N-stage filtration mechanisms to ensure that oil maintains a continuous filtration effect as it passes through each stage of the filtration mechanism. Specifically, firstly, N sets of filtration monitoring datasets corresponding to the N-stage filtration mechanisms are collected. Each set of filtration monitoring datasets includes the oil medium flow rate, oil pressure difference, oil medium temperature, oil contaminant concentration before filtration, and oil contaminant concentration after filtration for the corresponding filtration mechanism, which are key indicators for evaluating filtration effect and continuity.

[0017] Furthermore, based on the collected N sets of filtration monitoring datasets, the efficiency of the N-stage filtration system is calculated. This calculation can be based on various factors, such as oil medium flow rate, pressure difference, temperature, and contaminant concentrations before and after filtration. The formula for calculating filtration efficiency may vary depending on the contaminants and the filtration system, but it generally takes the following form: Filtration efficiency = (contaminant concentration before filtration - contaminant concentration after filtration) / contaminant concentration before filtration × 100%. Output N filtration efficiency values, each value corresponding to the filtration effect of the first-stage filtration mechanism.

[0018] Furthermore, after obtaining N filtration efficiency values, these values ​​are grouped according to the order of the filtration mechanisms, generating N-1 filtration efficiency groups. Each group contains the filtration efficiency values ​​of two adjacent filtration stages. A filtration efficiency continuity analysis is then performed on these N-1 filtration efficiency groups to assess whether the filtration effect between adjacent filtration stages is continuous and stable. By analyzing the differences and trends of adjacent filtration efficiency values, N-1 filtration continuity indicators are output. These indicators reflect the continuity of the filtration effect of oil as it passes through each filtration stage, providing an important basis for subsequent identification and optimization of abnormal filtration mechanisms.

[0019] Furthermore, step P24 in this embodiment of the application also includes: P24-1: Calculate the cumulative probability for each of the N-1 filtration efficiency groups and output the N-1 cumulative probability, where the cumulative probability is the cumulative probability caused by the previous filtration mechanism to the next filtration mechanism in each filtration efficiency group; P24-2: Perform fitting calculation based on the N-1 cumulative probability and output N-1 filtration continuity indicators.

[0020] Optionally, when performing a continuity analysis of filtration efficiency for N-1 filtration efficiency groups, firstly, for each filtration efficiency group, the filtration efficiency data of the preceding filtration unit is analyzed. Then, based on this data, the cumulative probability of the preceding filtration unit affecting the following filtration unit is calculated. This cumulative probability reflects the potential impact of contaminants not completely removed by the preceding filtration unit on the following filtration unit. Through calculation, N-1 cumulative probability values ​​are output, each corresponding to a filtration efficiency group.

[0021] Furthermore, a fitting calculation is performed based on the N-1 cumulative probability. This fitting calculation involves statistical analysis, mathematical model construction, and parameter optimization of the cumulative probability data to reveal the relationship between the cumulative probability and the filtration continuity. Through this fitting calculation, the module can more accurately assess the filtration continuity between adjacent filtration stages, thereby outputting more reliable N-1 filtration continuity indicators. These filtration continuity indicators will serve as an important basis for subsequent identification and feedback optimization of abnormal filtration stages, helping the system achieve more precise quality control.

[0022] Furthermore, step P24-2 in the embodiments of this application also includes: P24-21: Based on the N-1 cumulative probabilities, take the first and second cumulative probabilities as the objects to be fitted, and output the second fitted cumulative probability under the condition of the first cumulative probability; P24-22: Take the second and third fitted cumulative probabilities as the objects to be fitted, and output the third fitted cumulative probability under the condition of the second fitted cumulative probability, and so on, output N-1 fitted cumulative probabilities; P24-23: Based on the N-1 fitted cumulative probabilities, output N-1 filtering continuity indicators.

[0023] Specifically, based on N-1 cumulative probabilities, the first cumulative probability (i.e., the cumulative probability caused by the first-level filtration mechanism to the second-level filtration mechanism) and the second cumulative probability (i.e., the cumulative probability caused by the second-level filtration mechanism to the third-level filtration mechanism) are first used as the objects to be fitted.

[0024] Using a suitable fitting method, such as linear fitting, polynomial fitting, exponential fitting, etc., output the second fitted cumulative probability under the condition of the first cumulative probability. The second fitted cumulative probability is a predicted or simulated value of the second cumulative probability based on the first cumulative probability.

[0025] Furthermore, using the second and third cumulative probabilities as new fitted objects, the same fitting method is applied to output the third cumulative probabilities under the condition of the second cumulative probabilities. This process is repeated until all cumulative probabilities have been used for fitting calculation, resulting in N-2 cumulative probabilities. These are then added to the first cumulative probability to output N-1 cumulative probabilities.

[0026] Furthermore, the continuity of the filtering is comprehensively evaluated based on the N-1 cumulative fitting probabilities.

[0027] By comparing the differences, trends, or other statistics between the original cumulative probabilities and N-1 fitted cumulative probabilities, N-1 filtering continuity indicators can be output. These indicators will quantitatively reflect the filtering continuity between different levels of filtering mechanisms, providing an important basis for subsequent identification of abnormal filtering mechanisms and feedback optimization.

[0028] Abnormal filtration mechanism determination module 13 is used to determine abnormal filtration mechanisms based on the N-1 filtration continuity indicators.

[0029] Furthermore, the anomaly filtering mechanism determination module 13 is also used to perform the following steps: P31: Determine the preset continuity index; P32: Perform a sequential traversal from the N-1 filter continuity indices to identify abnormal filter mechanisms that are greater than the preset continuity index.

[0030] In one possible embodiment of this application, the abnormal filtering mechanism determination module 13 primarily functions to determine abnormal filtering mechanisms based on N-1 filtering continuity indicators. First, based on historical data, industry standards, or expert experience, one or more preset continuity indicators are set to determine whether the filtering continuity is normal. The preset continuity indicator may be a fixed value, a range, or a threshold. Further, the N-1 filtering continuity indicators are sequentially traversed, comparing the magnitude of each indicator with the preset continuity indicator. If a filtering continuity indicator is greater than the preset continuity indicator, it means that the filtering mechanism corresponding to that indicator is abnormal; that is, the cumulative impact of the previous level filtering mechanism on the next level filtering mechanism exceeds the normal range, meaning the continuity between adjacent levels of filtering mechanisms is not good. The filtering mechanism corresponding to this indicator is then marked as an abnormal filtering mechanism for further processing or maintenance.

[0031] Feedback analysis module 14 is used to identify the mechanism configuration parameters of the abnormal filtering mechanism and input the mechanism configuration parameters of the abnormal filtering mechanism into the adaptive feedback module for feedback analysis. The adaptive feedback module is a cascaded feedback module, including a parallel feedback module and a series feedback module.

[0032] Furthermore, the feedback analysis module 14 is also used to perform the following steps: P41: Set a parallel optimization scheme at the same level, which is used to set a parallel filtering mechanism at the level where the abnormal filtering mechanism is located; P42: The adaptive feedback module performs filtering performance analysis on the parallel optimization scheme at the same level and obtains the parallel-performance improvement index; P43: Obtain the parallel fitness index according to the parallel-performance improvement index.

[0033] It should be understood that the feedback analysis module 14 of this application is mainly responsible for identifying the mechanism configuration parameters of the anomaly filtering mechanism and inputting them into the adaptive feedback module for in-depth analysis to determine whether it is necessary to configure parallel mechanisms of the same level to improve performance. The adaptive feedback module adopts a cascaded feedback structure, specifically including parallel feedback modules and series feedback modules, to adapt to different optimization needs.

[0034] Specifically, upon identifying an abnormal filter mechanism, multiple parallel optimization schemes are first set up for it. These parallel optimization schemes aim to distribute the filtration load and improve filtration efficiency by adding parallel filter mechanisms at the same level as the abnormal filter mechanism. Furthermore, the parallel feedback module in the adaptive feedback module performs filtration performance analysis on the multiple parallel optimization schemes, evaluating the performance improvement of the entire filtration system after adding parallel filter mechanisms. A parallel performance improvement index can be obtained through simulation calculations or actual testing; this index reflects the specific degree of improvement in filtration performance brought about by the parallel optimization schemes.

[0035] Furthermore, based on the aforementioned parallel-performance improvement index, and taking into account factors such as the degree of improvement in filtration performance, cost investment, and operational complexity of the parallel optimization scheme, each factor is quantified and weighted to obtain the parallel fitness index of each parallel optimization scheme at the same level, which is used to evaluate the feasibility and effectiveness of each scheme in practical applications.

[0036] Parallel feedback optimization module 15 is used to obtain a parallel fitness index based on the adaptive feedback module. If the parallel fitness index meets a preset threshold, the abnormal filtering mechanism is optimized by parallel feedback.

[0037] Furthermore, such as Figure 3As shown, the parallel feedback optimization module 15 is further configured to perform the following steps: P51: If the parallel fitness index meets the preset threshold, obtain a parallel instruction; P52: According to the parallel instruction, optimize from the same-level parallel optimization schemes to obtain a first parallel optimization scheme, wherein the first parallel optimization scheme is the scheme with the largest performance improvement index among the same-level parallel optimization schemes; P53: Set a parallel filtering mechanism at the level where the abnormal filtering mechanism is located according to the first parallel optimization scheme.

[0038] Optionally, the parallel feedback optimization module 15 of this application is mainly responsible for performing parallel feedback optimization on the anomaly filtering mechanism based on the analysis results of the adaptive feedback module. First, it checks whether the parallel fitness index of each parallel optimization scheme at the same level output by the adaptive feedback module meets a preset threshold. The preset threshold is set based on factors such as system performance requirements, cost considerations, and operational complexity, and is used to determine whether the parallel optimization scheme is worth implementing. If the parallel fitness index of each parallel optimization scheme at the same level meets the preset threshold, a parallel instruction is generated, and the performance improvement index of each parallel optimization scheme at the same level is compared. The scheme with the largest performance improvement index is selected as the first parallel optimization scheme.

[0039] Furthermore, according to the first parallel optimization scheme, a parallel filtration mechanism is set up at the stage where the abnormal filtration mechanism is located to improve the overall performance of the filtration system and ensure the stable and efficient operation of the petroleum grading filtration device.

[0040] The series feedback optimization module 16 is used to perform series feedback optimization on the anomaly filtering mechanism if the parallel fitness index does not meet the preset threshold.

[0041] Furthermore, the series feedback optimization module 16 is also used to perform the following steps: P61: Set a series optimization scheme, which is used to add a series filter mechanism between the abnormal filter mechanism and the filter mechanism above the abnormal filter mechanism; P62: The adaptive feedback module performs a filtering performance analysis on the series optimization scheme to obtain a series-performance improvement index; P63: Optimize the series optimization scheme according to the series-performance improvement index to obtain a first series optimization scheme; P64: Add a series filter mechanism between the abnormal filter mechanism and the filter mechanism above the abnormal filter mechanism according to the first series optimization scheme.

[0042] Specifically, the series feedback optimization module 16 of this application is mainly responsible for performing series feedback optimization when the parallel fitness index of the parallel feedback optimization module does not meet the preset threshold. Specifically, when the parallel fitness index does not meet the preset threshold, it indicates that the parallel solution cannot solve the problem, so the series feedback optimization module 16 starts working. First, a series optimization scheme is set between the abnormal filtration mechanism and the previous filtration mechanism. The core idea of ​​the series optimization scheme is to add a series filtration mechanism between the two to improve the overall filtration efficiency or optimize the removal effect of specific pollutants.

[0043] Furthermore, the adaptive feedback module performs a filtering performance analysis on the series optimization scheme, including evaluating the impact of the newly added series filtering mechanism on the overall filtration system performance through simulation calculations or actual tests. The analysis results will be converted into a series-performance improvement index to quantitatively evaluate the effectiveness of the optimization scheme.

[0044] Furthermore, after obtaining the series-performance improvement indicators of multiple series optimization schemes, the series optimization scheme is optimized according to these indicators. By comparing the performance improvement degree, cost investment, and operational complexity of different series optimization schemes, and performing comprehensive fitness calculations, the scheme with the largest performance improvement indicator and the best overall cost-effectiveness is finally selected as the first series optimization scheme. Then, based on the selected first series optimization scheme, the system is guided to add a series filtering mechanism in actual operation. The added series filtering mechanism will be placed between the abnormal filtering mechanism and the previous filtering mechanism to improve the overall performance of the filtration system. The series feedback optimization module 16 can provide another effective optimization approach for the petroleum grading filtration device when the parallel optimization scheme is not feasible, thereby improving the operational stability of the system.

[0045] In summary, the embodiments of this application have at least the following technical effects: This application obtains N sets of filtration monitoring datasets for N-stage filtration mechanisms in a petroleum grading filtration device, performs filtration continuity analysis, identifies abnormal filtration mechanisms, identifies the mechanism configuration parameters of abnormal filtration mechanisms, inputs them into an adaptive feedback module for feedback analysis, and performs parallel feedback optimization or series feedback optimization on abnormal filtration mechanisms based on the analysis results.

[0046] This technology achieves the goal of improving oil filtration efficiency and stability through real-time monitoring, precise diagnosis, and flexible feedback optimization of multi-stage filtration mechanisms.

[0047] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0048] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0049] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. An intelligent petroleum grading filtration control system with a cascading feedback function, characterized by, The system comprises: a filtering mechanism acquisition module for acquiring N-stage filtering mechanisms of an oil grading filtering device, N being a positive integer greater than or equal to 2; a filtering continuity analysis module for monitoring N sets of filtering monitoring data corresponding to the N-stage filtering mechanisms, performing filtering continuity analysis on filtering monitoring data sets of adjacent two sets of the N sets of filtering monitoring data, and outputting N-1 filtering continuity indexes; an abnormal filtering mechanism determination module for determining an abnormal filtering mechanism according to the N-1 filtering continuity indexes; a feedback analysis module for identifying mechanism configuration parameters of the abnormal filtering mechanism and inputting the mechanism configuration parameters of the abnormal filtering mechanism into a self-adaptive feedback module for feedback analysis, wherein the self-adaptive feedback module is a cascaded feedback module comprising a parallel feedback module and a serial feedback module; a parallel feedback optimization module for acquiring a parallel fitness index according to the self-adaptive feedback module, and performing parallel feedback optimization on the abnormal filtering mechanism if the parallel fitness index meets a preset threshold; a serial feedback optimization module for performing serial feedback optimization on the abnormal filtering mechanism if the parallel fitness index does not meet the preset threshold.

2. The intelligent petroleum grading filtration control system with cascade feedback function according to claim 1, characterized in that, performing filtering continuity analysis on filtering monitoring data sets of adjacent two sets of the N sets of filtering monitoring data, comprises: wherein each set of filtering monitoring data comprises oil medium flow, oil pressure difference, oil medium temperature, oil pollutant concentration before filtering, and oil pollutant concentration after filtering of a corresponding filtering mechanism; calculating efficiency of the N-stage filtering mechanisms according to the N sets of filtering monitoring data, and outputting N filtering efficiencies; generating N-1 filtering efficiency groups corresponding to adjacent two groups of the N filtering efficiencies; performing filtering efficiency continuity analysis on the N-1 filtering efficiency groups, and outputting N-1 filtering continuity indexes.

3. The intelligent petroleum grading filtration control system with cascade feedback function according to claim 2, characterized in that, performing filtering efficiency continuity analysis on the N-1 filtering efficiency groups, and outputting N-1 filtering continuity indexes, comprises: performing cumulative probability calculation on each filtering efficiency group of the N-1 filtering efficiency groups, and outputting N-1 cumulative probabilities, wherein the cumulative probability is a cumulative probability of a previous-stage filtering mechanism to a next-stage filtering mechanism in each filtering efficiency group; performing fitting calculation according to the N-1 cumulative probabilities, and outputting N-1 filtering continuity indexes.

4. The intelligent petroleum grading filtration control system with cascade feedback function according to claim 3, characterized in that, performing fitting calculation according to the N-1 cumulative probabilities, comprises: taking a first cumulative probability and a second cumulative probability as objects to be fitted according to the N-1 cumulative probabilities, and outputting a second fitted cumulative probability under the condition of the first cumulative probability; taking the second fitted cumulative probability and a third cumulative probability as objects to be fitted, and outputting a third fitted cumulative probability under the condition of the second fitted cumulative probability, and so on, to output N-1 fitted cumulative probabilities; outputting N-1 filtering continuity indexes according to the N-1 fitted cumulative probabilities.

5. The intelligent petroleum grading filtration control system with cascade feedback function according to claim 1, characterized in that, According to the N-1 filter continuity indexes, determining an abnormal filter mechanism, comprising: Determining a preset continuity index; From the N-1 filter continuity indexes, sequentially traversing to identify an abnormal filter mechanism greater than the preset continuity index.

6. The intelligent petroleum grading filtration control system with cascade feedback function according to claim 1, characterized in that, Inputting the mechanism configuration parameters of the abnormal filter mechanism into an adaptive feedback module for feedback analysis, comprising: Setting a same-level parallel optimization scheme, which is used to set a parallel filter mechanism for the level where the abnormal filter mechanism is located; The adaptive feedback module performs filter performance analysis on the same-level parallel optimization scheme to obtain a parallel-performance improvement index; According to the parallel-performance improvement index, obtaining a parallel fitness index.

7. The intelligent petroleum grading filtration control system with cascade feedback function according to claim 6, characterized in that, If the parallel fitness index meets a preset threshold, performing parallel feedback optimization on the abnormal filter mechanism, comprising: If the parallel fitness index meets the preset threshold, obtaining a parallel instruction; According to the parallel instruction, performing optimization from the same-level parallel optimization scheme to obtain a first parallel optimization scheme, wherein the first parallel optimization scheme is the scheme with the largest performance improvement index in the same-level parallel optimization scheme; According to the first parallel optimization scheme, setting a parallel filter mechanism for the level where the abnormal filter mechanism is located.

8. The intelligent petroleum grading filtration control system with cascade feedback function according to claim 1, characterized in that, If the parallel fitness index does not meet the preset threshold, performing series feedback optimization on the abnormal filter mechanism, comprising: Setting a series optimization scheme, which is used to add a series filter mechanism between the abnormal filter mechanism and the previous filter mechanism of the abnormal filter mechanism; The adaptive feedback module performs filter performance analysis on the series optimization scheme to obtain a series-performance improvement index; According to the series-performance improvement index, performing optimization from the series optimization scheme to obtain a first series optimization scheme; According to the first series optimization scheme, adding a series filter mechanism between the abnormal filter mechanism and the previous filter mechanism of the abnormal filter mechanism.

Images